summaryrefslogtreecommitdiffstats
path: root/util/unicode/data/WordBreakProperty.txt
diff options
context:
space:
mode:
authorIevgenii Meshcheriakov <ievgenii.meshcheriakov@qt.io>2024-01-25 12:18:48 +0100
committerMårten Nordheim <marten.nordheim@qt.io>2024-02-08 16:43:58 +0000
commitbfd09ec38c43551db17bd01a0ad5fb161babd840 (patch)
tree47a83edfa0a160f8a16502d666b211960f1dbe3c /util/unicode/data/WordBreakProperty.txt
parent25b89f2c88cdfc98bfa462949531a33f7ef50996 (diff)
unicode: Import version 15.1 (UCD version 32)
Add enumerator for the new Unicode version to QChar::UnicodeVersion. Remap new line breaking classes to their Unicode 15.0 values: * AK, AP and AS to AL, * VI and VF to CM. These are classes for new line breaking support for Indic scripts that require more work. Blacklist failing tests for now: * tst_QUrlUts46::idnaTestV2 * tst_QTextBoundaryFinder::lineBoundariesDefault * tst_QTextBoundaryFinder::graphemeBoundariesDefault Regenerate the source files. Task-number: QTBUG-121529 Change-Id: I869cc9fbaa53765d8ae6265c22cdbef9f19d05bf Reviewed-by: Mårten Nordheim <marten.nordheim@qt.io> Reviewed-by: Edward Welbourne <edward.welbourne@qt.io>
Diffstat (limited to 'util/unicode/data/WordBreakProperty.txt')
-rw-r--r--util/unicode/data/WordBreakProperty.txt26
1 files changed, 13 insertions, 13 deletions
diff --git a/util/unicode/data/WordBreakProperty.txt b/util/unicode/data/WordBreakProperty.txt
index 6f868d21f3..302a2769b3 100644
--- a/util/unicode/data/WordBreakProperty.txt
+++ b/util/unicode/data/WordBreakProperty.txt
@@ -1,6 +1,6 @@
-# WordBreakProperty-15.0.0.txt
-# Date: 2022-04-27, 02:41:26 GMT
-# © 2022 Unicode®, Inc.
+# WordBreakProperty-15.1.0.txt
+# Date: 2023-03-31, 03:19:05 GMT
+# © 2023 Unicode®, Inc.
# Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries.
# For terms of use, see https://www.unicode.org/terms_of_use.html
#
@@ -615,12 +615,7 @@ E0100..E01EF ; Extend # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256
# ================================================
00AD ; Format # Cf SOFT HYPHEN
-0600..0605 ; Format # Cf [6] ARABIC NUMBER SIGN..ARABIC NUMBER MARK ABOVE
061C ; Format # Cf ARABIC LETTER MARK
-06DD ; Format # Cf ARABIC END OF AYAH
-070F ; Format # Cf SYRIAC ABBREVIATION MARK
-0890..0891 ; Format # Cf [2] ARABIC POUND MARK ABOVE..ARABIC PIASTRE MARK ABOVE
-08E2 ; Format # Cf ARABIC DISPUTED END OF AYAH
180E ; Format # Cf MONGOLIAN VOWEL SEPARATOR
200E..200F ; Format # Cf [2] LEFT-TO-RIGHT MARK..RIGHT-TO-LEFT MARK
202A..202E ; Format # Cf [5] LEFT-TO-RIGHT EMBEDDING..RIGHT-TO-LEFT OVERRIDE
@@ -628,14 +623,12 @@ E0100..E01EF ; Extend # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256
2066..206F ; Format # Cf [10] LEFT-TO-RIGHT ISOLATE..NOMINAL DIGIT SHAPES
FEFF ; Format # Cf ZERO WIDTH NO-BREAK SPACE
FFF9..FFFB ; Format # Cf [3] INTERLINEAR ANNOTATION ANCHOR..INTERLINEAR ANNOTATION TERMINATOR
-110BD ; Format # Cf KAITHI NUMBER SIGN
-110CD ; Format # Cf KAITHI NUMBER SIGN ABOVE
13430..1343F ; Format # Cf [16] EGYPTIAN HIEROGLYPH VERTICAL JOINER..EGYPTIAN HIEROGLYPH END WALLED ENCLOSURE
1BCA0..1BCA3 ; Format # Cf [4] SHORTHAND FORMAT LETTER OVERLAP..SHORTHAND FORMAT UP STEP
1D173..1D17A ; Format # Cf [8] MUSICAL SYMBOL BEGIN BEAM..MUSICAL SYMBOL END PHRASE
E0001 ; Format # Cf LANGUAGE TAG
-# Total code points: 71
+# Total code points: 58
# ================================================
@@ -718,6 +711,7 @@ FF71..FF9D ; Katakana # Lo [45] HALFWIDTH KATAKANA LETTER A..HALFWIDTH KATAK
06EE..06EF ; ALetter # Lo [2] ARABIC LETTER DAL WITH INVERTED V..ARABIC LETTER REH WITH INVERTED V
06FA..06FC ; ALetter # Lo [3] ARABIC LETTER SHEEN WITH DOT BELOW..ARABIC LETTER GHAIN WITH DOT BELOW
06FF ; ALetter # Lo ARABIC LETTER HEH WITH INVERTED V
+070F ; ALetter # Cf SYRIAC ABBREVIATION MARK
0710 ; ALetter # Lo SYRIAC LETTER ALAPH
0712..072F ; ALetter # Lo [30] SYRIAC LETTER BETH..SYRIAC LETTER PERSIAN DHALATH
074D..07A5 ; ALetter # Lo [89] SYRIAC LETTER SOGDIAN ZHAIN..THAANA LETTER WAAVU
@@ -1319,7 +1313,7 @@ FFDA..FFDC ; ALetter # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL
1F150..1F169 ; ALetter # So [26] NEGATIVE CIRCLED LATIN CAPITAL LETTER A..NEGATIVE CIRCLED LATIN CAPITAL LETTER Z
1F170..1F189 ; ALetter # So [26] NEGATIVE SQUARED LATIN CAPITAL LETTER A..NEGATIVE SQUARED LATIN CAPITAL LETTER Z
-# Total code points: 29489
+# Total code points: 29490
# ================================================
@@ -1369,10 +1363,14 @@ FF0E ; MidNumLet # Po FULLWIDTH FULL STOP
# ================================================
0030..0039 ; Numeric # Nd [10] DIGIT ZERO..DIGIT NINE
+0600..0605 ; Numeric # Cf [6] ARABIC NUMBER SIGN..ARABIC NUMBER MARK ABOVE
0660..0669 ; Numeric # Nd [10] ARABIC-INDIC DIGIT ZERO..ARABIC-INDIC DIGIT NINE
066B ; Numeric # Po ARABIC DECIMAL SEPARATOR
+06DD ; Numeric # Cf ARABIC END OF AYAH
06F0..06F9 ; Numeric # Nd [10] EXTENDED ARABIC-INDIC DIGIT ZERO..EXTENDED ARABIC-INDIC DIGIT NINE
07C0..07C9 ; Numeric # Nd [10] NKO DIGIT ZERO..NKO DIGIT NINE
+0890..0891 ; Numeric # Cf [2] ARABIC POUND MARK ABOVE..ARABIC PIASTRE MARK ABOVE
+08E2 ; Numeric # Cf ARABIC DISPUTED END OF AYAH
0966..096F ; Numeric # Nd [10] DEVANAGARI DIGIT ZERO..DEVANAGARI DIGIT NINE
09E6..09EF ; Numeric # Nd [10] BENGALI DIGIT ZERO..BENGALI DIGIT NINE
0A66..0A6F ; Numeric # Nd [10] GURMUKHI DIGIT ZERO..GURMUKHI DIGIT NINE
@@ -1409,6 +1407,8 @@ FF10..FF19 ; Numeric # Nd [10] FULLWIDTH DIGIT ZERO..FULLWIDTH DIGIT NINE
104A0..104A9 ; Numeric # Nd [10] OSMANYA DIGIT ZERO..OSMANYA DIGIT NINE
10D30..10D39 ; Numeric # Nd [10] HANIFI ROHINGYA DIGIT ZERO..HANIFI ROHINGYA DIGIT NINE
11066..1106F ; Numeric # Nd [10] BRAHMI DIGIT ZERO..BRAHMI DIGIT NINE
+110BD ; Numeric # Cf KAITHI NUMBER SIGN
+110CD ; Numeric # Cf KAITHI NUMBER SIGN ABOVE
110F0..110F9 ; Numeric # Nd [10] SORA SOMPENG DIGIT ZERO..SORA SOMPENG DIGIT NINE
11136..1113F ; Numeric # Nd [10] CHAKMA DIGIT ZERO..CHAKMA DIGIT NINE
111D0..111D9 ; Numeric # Nd [10] SHARADA DIGIT ZERO..SHARADA DIGIT NINE
@@ -1434,7 +1434,7 @@ FF10..FF19 ; Numeric # Nd [10] FULLWIDTH DIGIT ZERO..FULLWIDTH DIGIT NINE
1E950..1E959 ; Numeric # Nd [10] ADLAM DIGIT ZERO..ADLAM DIGIT NINE
1FBF0..1FBF9 ; Numeric # Nd [10] SEGMENTED DIGIT ZERO..SEGMENTED DIGIT NINE
-# Total code points: 681
+# Total code points: 693
# ================================================